INDEX

Explanations

proper nouns and organizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĿª

-0.14

 Cure

-0.14

em

-0.14

ire

-0.14

MB

-0.13

fang

-0.13

 addCriterion

-0.13

ulus

-0.13

 closure

-0.13

 seal

-0.13

POSITIVE LOGITS

elu

0.17

 Wagner

0.15

erli

0.15

alion

0.15

/inet

0.14

utut

0.14

egl

0.14

licer

0.14

 cÃ©lib

0.14

IGHL

0.14

Activations Density 0.038%

proper nouns and organizations

No Comments

No Known Activations